Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2996 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.8080. Min Act: -0.1700

Data Index: 7586214 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7454. Min Act: -0.1700

Data Index: 8546085 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 6649586 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 4499346 (Open Web Text)

Max Activating Token Index: 733

Text #4

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 4600226 (Open Web Text)

Max Activating Token Index: 620

Text #5

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 4263993 (Open Web Text)

Max Activating Token Index: 663

Text #6

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.7141. Min Act: -0.1700

Data Index: 3932022 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6828. Min Act: -0.1700

Data Index: 8153776 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6516. Min Act: -0.1700

Data Index: 6649688 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6203. Min Act: -0.1700

Data Index: 4048878 (Open Web Text)

Max Activating Token Index: 528

Text #10

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.6203. Min Act: -0.1700

Data Index: 5178056 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5576. Min Act: -0.1700

Data Index: 1486170 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5576. Min Act: -0.1700

Data Index: 7642137 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 5306439 (Open Web Text)

Max Activating Token Index: 362

Text #14

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 2347675 (Open Web Text)

Max Activating Token Index: 285

Text #15

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 243001 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 4870460 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 8694083 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 233570 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 3.8080. Min Range: -3.8080

Max Act: 3.5263. Min Act: -0.1700

Data Index: 131543 (Open Web Text)

Max Activating Token Index: 646